Model: GELU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1056 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.8687. Min Range: -3.8687

Max Act: 3.8687. Min Act: -0.1700

Data Index: 1313570 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 3.8687. Min Range: -3.8687

Max Act: 3.8530. Min Act: -0.1700

Data Index: 91114 (C4 (Web Text))

Max Activating Token Index: 805

Text #2

Max Range: 3.8687. Min Range: -3.8687

Max Act: 3.8374. Min Act: -0.1700

Data Index: 328222 (C4 (Web Text))

Max Activating Token Index: 373

Text #3

Max Range: 3.8687. Min Range: -3.8687

Max Act: 3.8218. Min Act: -0.1700

Data Index: 255777 (C4 (Web Text))

Max Activating Token Index: 250

Text #4

Max Range: 3.8687. Min Range: -3.8687

Max Act: 3.8218. Min Act: -0.1700

Data Index: 506460 (C4 (Web Text))

Max Activating Token Index: 524

Text #5

Max Range: 3.8687. Min Range: -3.8687

Max Act: 3.7905. Min Act: -0.1700

Data Index: 423539 (C4 (Web Text))

Max Activating Token Index: 444

Text #6

Max Range: 3.8687. Min Range: -3.8687

Max Act: 3.7905. Min Act: -0.1700

Data Index: 75451 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 3.8687. Min Range: -3.8687

Max Act: 3.7905. Min Act: -0.1700

Data Index: 40514 (C4 (Web Text))

Max Activating Token Index: 867

Text #8

Max Range: 3.8687. Min Range: -3.8687

Max Act: 3.7905. Min Act: -0.1700

Data Index: 527910 (C4 (Web Text))

Max Activating Token Index: 81

Text #9

Max Range: 3.8687. Min Range: -3.8687

Max Act: 3.7592. Min Act: -0.1700

Data Index: 788564 (C4 (Web Text))

Max Activating Token Index: 491

Text #10

Max Range: 3.8687. Min Range: -3.8687

Max Act: 3.7592. Min Act: -0.1700

Data Index: 657280 (C4 (Web Text))

Max Activating Token Index: 740

Text #11

Max Range: 3.8687. Min Range: -3.8687

Max Act: 3.7592. Min Act: -0.1700

Data Index: 189646 (C4 (Web Text))

Max Activating Token Index: 663

Text #12

Max Range: 3.8687. Min Range: -3.8687

Max Act: 3.7436. Min Act: -0.1700

Data Index: 812218 (C4 (Web Text))

Max Activating Token Index: 525

Text #13

Max Range: 3.8687. Min Range: -3.8687

Max Act: 3.7123. Min Act: -0.1700

Data Index: 436828 (C4 (Web Text))

Max Activating Token Index: 908

Text #14

Max Range: 3.8687. Min Range: -3.8687

Max Act: 3.7279. Min Act: -0.1700

Data Index: 480210 (C4 (Web Text))

Max Activating Token Index: 215

Text #15

Max Range: 3.8687. Min Range: -3.8687

Max Act: 3.7279. Min Act: -0.1700

Data Index: 652853 (C4 (Web Text))

Max Activating Token Index: 801

Text #16

Max Range: 3.8687. Min Range: -3.8687

Max Act: 3.7436. Min Act: -0.1700

Data Index: 19940 (C4 (Web Text))

Max Activating Token Index: 329

Text #17

Max Range: 3.8687. Min Range: -3.8687

Max Act: 3.7279. Min Act: -0.1700

Data Index: 720350 (C4 (Web Text))

Max Activating Token Index: 977

Text #18

Max Range: 3.8687. Min Range: -3.8687

Max Act: 3.7279. Min Act: -0.1700

Data Index: 312355 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 3.8687. Min Range: -3.8687

Max Act: 3.7123. Min Act: -0.1700

Data Index: 7088 (C4 (Web Text))

Max Activating Token Index: 42